Interpreting deep learning models for epileptic seizure detection on EEG signals

While Deep Learning (DL) is often considered the state-of-the art for Artificial Intelligence-based medical decision support, it remains sparsely implemented in clinical practice and poorly trusted by clinicians due to insufficient interpretability of neural network models. We have tackled this issue by developing interpretable DL models in the context of online detection of epileptic seizure, based on EEG signal. This has conditioned the preparation of the input signals, the network architecture, and the post-processing of the output in line with the domain knowledge. Specifically, we focused the discussion on three main aspects: 1) how to aggregate the classification results on signal segments provided by the DL model into a larger time scale, at the seizure-level; 2) what are the relevant frequency patterns learned in the first convolutional layer of different models, and their relation with the delta, theta, alpha, beta and gamma frequency bands on which the visual interpretation of EEG is based; and 3) the identification of the signal waveforms with larger contribution towards the ictal class, according to the activation differences highlighted using the DeepLIFT method. Results show that the kernel size in the first layer determines the interpretability of the extracted features and the sensitivity of the trained models, even though the final performance is very similar after post-processing. Also, we found that amplitude is the main feature leading to an ictal prediction, suggesting that a larger patient population would be required to learn more complex frequency patterns. Still, our methodology was successfully able to generalize patient inter-variability for the majority of the studied population with a classification F1-score of 0.873 and detecting 90% of the seizures.

From Classical to Unsupervised-Deep-Learning Methods for Solving Inverse Problems in Imaging.

Harshit Gupta

In this thesis, we propose new algorithms to solve inverse problems in the context of biomedical images. Due to ill-posedness, solving these problems require some prior knowledge of the statistics of the underlying images. The traditional algorithms, in the field, assume prior knowledge related to smoothness or sparsity of these images. Recently, they have been outperformed by the second generation algorithms which harness the power of neural networks to learn required statistics from training data. Even more recently, last generation deep-learning-based methods have emerged which require neither training nor training data. This thesis devises algorithms which progress through these generations. It extends these generations to novel formulations and applications while bringing more robustness. In parallel, it also progresses in terms of complexity, from proposing algorithms for problems with 1D data and an exact known forward model to the ones with 4D data and an unknown parametric forward model. We introduce five main contributions. The last three of them propose deep-learning-based latest-generation algorithms that require no prior training. 1) We develop algorithms to solve the continuous-domain formulation of inverse problems with both classical Tikhonov and total-variation regularizations. We formalize the problems, characterize the solution set, and devise numerical approaches to find the solutions. 2) We propose an algorithm that improves upon end-to-end neural-network-based second generation algorithms. In our method, a neural network is first trained as a projector on a training set, and is then plugged in as a projector inside the projected gradient descent (PGD). Since the problem is nonconvex, we relax the PGD to ensure convergence to a local minimum under some constraints. This method outperforms all the previous generation algorithms for Computed Tomography (CT). 3) We develop a novel time-dependent deep-image-prior algorithm for modalities that involve a temporal sequence of images. We parameterize them as the output of an untrained neural network fed with a sequence of latent variables. To impose temporal directionality, the latent variables are assumed to lie on a 1D manifold. The network is then tuned to minimize the data fidelity. We obtain state-of-the-art results in dynamic magnetic resonance imaging (MRI) and even recover intra-frame images. 4) We propose a novel reconstruction paradigm for cryo-electron-microscopy (CryoEM) called CryoGAN. Motivated by generative adversarial networks (GANs), we reconstruct a biomolecule's 3D structure such that its CryoEM measurements resemble the acquired data in a distributional sense. The algorithm is pose-or-likelihood-estimation-free, needs no ab initio, and is proven to have a theoretical guarantee of recovery of the true structure. 5) We extend CryoGAN to reconstruct continuously varying conformations of a structure from heterogeneous data. We parameterize the conformations as the output of a neural network fed with latent variables on a low-dimensional manifold. The method is shown to recover continuous protein conformations and their energy landscape.

EPFL2020

Zero-Learning Fast Medical Image Fusion

Fayez Lahoud, Sabine Süsstrunk

Clinical applications, such as image-guided surgery and noninvasive diagnosis, rely heavily on multi-modal images. Medical image fusion plays a central role by integrating information from multiple sources into a single, more understandable output. We propose a real-time image fusion method using pretrained neural networks to generate a single image containing features from multi-modal sources. The images are merged using a novel strategy based on deep feature maps extracted from a convolutional neural network. These feature maps are compared to generate fusion weights that drive the multi-modal image fusion process. Our method is not limited to the fusion of two images, it can be applied to any number of input sources. We validate the effectiveness of our proposed method on multiple medical fusion categories. The experimental results demonstrate that our technique achieves state-of-the-art performance in both visual quality, objective assessment, and runtime efficiency.

2019

Using DeepLabCut for 3D markerless pose estimation across species and behaviors

An Chi Chen, Mackenzie Mathis, Alexander Mathis, Tanmay Nath

Noninvasive behavioral tracking of animals during experiments is crucial to many scientific pursuits. Extracting the poses of animals without using markers is often essential for measuring behavioral effects in biomechanics, genetics, ethology & neuroscience. Yet, extracting detailed poses without markers in dynamically changing backgrounds has been challenging. We recently introduced an open source toolbox called DeepLabCut that builds on a state-of-the-art human pose estimation algorithm to allow a user to train a deep neural network using limited training data to precisely track user-defined features that matches human labeling accuracy. Here, with this paper we provide an updated toolbox that is self contained within a Python package that includes new features such as graphical user interfaces and active-learning based network refinement. Lastly, we provide a step-by-step guide for using DeepLabCut.

Neuroscience2018

From Classical to Unsupervised-Deep-Learning Methods for Solving Inverse Problems in Imaging.

Harshit Gupta

EPFL2020